Initial commit

README.md

@@ -16,7 +16,7 @@ model-index:
       type: AntBulletEnv-v0
     metrics:
     - type: mean_reward
-      value: 8.40 +/- 0.29
+      value: 1713.61 +/- 89.07
       name: mean_reward
       verified: false
 ---

a2c-AntBulletEnv-v0.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1a1ae24f79dae123f3d4b654dd4631a0a4a5b063c82064310bb8c0484d45c419
-size 67573
+oid sha256:0b2cd0704e0c4f9b3ca10ab8400f0e58610a91f316f75ed053abcca1e69dfcce
+size 129260

a2c-AntBulletEnv-v0/data

@@ -4,20 +4,20 @@
         ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==",
         "__module__": "stable_baselines3.common.policies",
         "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ",
-        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f223d3f03a0>",
-        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f223d3f0430>",
-        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f223d3f04c0>",
-        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f223d3f0550>",
-        "_build": "<function ActorCriticPolicy._build at 0x7f223d3f05e0>",
-        "forward": "<function ActorCriticPolicy.forward at 0x7f223d3f0670>",
-        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f223d3f0700>",
-        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f223d3f0790>",
-        "_predict": "<function ActorCriticPolicy._predict at 0x7f223d3f0820>",
-        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f223d3f08b0>",
-        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f223d3f0940>",
-        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f223d3f09d0>",
+        "__init__": "<function ActorCriticPolicy.__init__ at 0x7f311c7a8940>",
+        "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f311c7a89d0>",
+        "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f311c7a8a60>",
+        "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f311c7a8af0>",
+        "_build": "<function ActorCriticPolicy._build at 0x7f311c7a8b80>",
+        "forward": "<function ActorCriticPolicy.forward at 0x7f311c7a8c10>",
+        "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f311c7a8ca0>",
+        "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f311c7a8d30>",
+        "_predict": "<function ActorCriticPolicy._predict at 0x7f311c7a8dc0>",
+        "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f311c7a8e50>",
+        "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f311c7a8ee0>",
+        "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f311c7a8f70>",
         "__abstractmethods__": "frozenset()",
-        "_abc_impl": "<_abc_data object at 0x7f223d3e4cc0>"
+        "_abc_impl": "<_abc_data object at 0x7f311c825480>"
     },
     "verbose": 1,
     "policy_kwargs": {
@@ -34,57 +34,68 @@
     },
     "observation_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
-        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
-        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
         "_shape": [
             28
         ],
         "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]",
         "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]",
-        "low_repr": "-inf",
-        "high_repr": "inf",
+        "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
+        "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]",
         "_np_random": null
     },
     "action_space": {
         ":type:": "<class 'gym.spaces.box.Box'>",
-        ":serialized:": "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",
+        ":serialized:": "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",
         "dtype": "float32",
-        "bounded_below": "[ True  True  True  True  True  True  True  True]",
-        "bounded_above": "[ True  True  True  True  True  True  True  True]",
         "_shape": [
             8
         ],
         "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]",
         "high": "[1. 1. 1. 1. 1. 1. 1. 1.]",
-        "low_repr": "-1.0",
-        "high_repr": "1.0",
+        "bounded_below": "[ True  True  True  True  True  True  True  True]",
+        "bounded_above": "[ True  True  True  True  True  True  True  True]",
         "_np_random": null
     },
     "n_envs": 4,
-    "num_timesteps": 0,
-    "_total_timesteps": 0,
+    "num_timesteps": 2000000,
+    "_total_timesteps": 2000000,
     "_num_timesteps_at_start": 0,
     "seed": null,
     "action_noise": null,
-    "start_time": null,
+    "start_time": 1677584450975645946,
     "learning_rate": 0.00096,
     "tensorboard_log": null,
     "lr_schedule": {
         ":type:": "<class 'function'>",
         ":serialized:": "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"
     },
-    "_last_obs": null,
-    "_last_episode_starts": null,
-    "_last_original_obs": null,
+    "_last_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
+    "_last_episode_starts": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="
+    },
+    "_last_original_obs": {
+        ":type:": "<class 'numpy.ndarray'>",
+        ":serialized:": "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"
+    },
     "_episode_num": 0,
     "use_sde": true,
     "sde_sample_freq": -1,
-    "_current_progress_remaining": 1,
-    "ep_info_buffer": null,
-    "ep_success_buffer": null,
-    "_n_updates": 0,
+    "_current_progress_remaining": 0.0,
+    "ep_info_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "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"
+    },
+    "ep_success_buffer": {
+        ":type:": "<class 'collections.deque'>",
+        ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="
+    },
+    "_n_updates": 62500,
     "n_steps": 8,
     "gamma": 0.99,
     "gae_lambda": 0.9,

a2c-AntBulletEnv-v0/policy.optimizer.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:763e6aa37fb83f8a1ec0724e39a562418a7d4e18293f64bc65670e025bf41c6e
-size 687
+oid sha256:3ec48a6a284b22eed0f361f250c64d3bb153cb2600eb6bb455dbb1a23dcfb569
+size 56190

a2c-AntBulletEnv-v0/policy.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e0b8f94cde905f0b357471adbaf102a8020e6442beb24b0d8d2dac2b9f89d826
+oid sha256:81819085cead150fea96f8245772bbb617ab3cf37d35b5d5cabb9afb9002342d
 size 56958

config.json

@@ -1 +1 @@
-{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f223d3f03a0>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f223d3f0430>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f223d3f04c0>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f223d3f0550>", "_build": "<function ActorCriticPolicy._build at 0x7f223d3f05e0>", "forward": "<function ActorCriticPolicy.forward at 0x7f223d3f0670>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f223d3f0700>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f223d3f0790>", "_predict": "<function ActorCriticPolicy._predict at 0x7f223d3f0820>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f223d3f08b0>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f223d3f0940>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f223d3f09d0>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f223d3e4cc0>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "_shape": [28], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", "low_repr": "-inf", "high_repr": "inf", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "low_repr": "-1.0", "high_repr": "1.0", "_np_random": null}, "n_envs": 4, "num_timesteps": 0, "_total_timesteps": 0, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": null, "learning_rate": 0.00096, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "gAWVwwIAAAAAAACMF2Nsb3VkcGlja2xlLmNsb3VkcGlja2xllIwOX21ha2VfZnVuY3Rpb26Uk5QoaACMDV9idWlsdGluX3R5cGWUk5SMCENvZGVUeXBllIWUUpQoSwFLAEsASwFLAUsTQwSIAFMAlE6FlCmMAV+UhZSMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZSMBGZ1bmOUS4JDAgABlIwDdmFslIWUKXSUUpR9lCiMC19fcGFja2FnZV9flIwYc3RhYmxlX2Jhc2VsaW5lczMuY29tbW9ulIwIX19uYW1lX1+UjB5zdGFibGVfYmFzZWxpbmVzMy5jb21tb24udXRpbHOUjAhfX2ZpbGVfX5SMSC91c3IvbG9jYWwvbGliL3B5dGhvbjMuOC9kaXN0LXBhY2thZ2VzL3N0YWJsZV9iYXNlbGluZXMzL2NvbW1vbi91dGlscy5weZR1Tk5oAIwQX21ha2VfZW1wdHlfY2VsbJSTlClSlIWUdJRSlIwcY2xvdWRwaWNrbGUuY2xvdWRwaWNrbGVfZmFzdJSMEl9mdW5jdGlvbl9zZXRzdGF0ZZSTlGgffZR9lChoFmgNjAxfX3F1YWxuYW1lX1+UjBljb25zdGFudF9mbi48bG9jYWxzPi5mdW5jlIwPX19hbm5vdGF0aW9uc19flH2UjA5fX2t3ZGVmYXVsdHNfX5ROjAxfX2RlZmF1bHRzX1+UTowKX19tb2R1bGVfX5RoF4wHX19kb2NfX5ROjAtfX2Nsb3N1cmVfX5RoAIwKX21ha2VfY2VsbJSTlEc/T3UQTVUdaYWUUpSFlIwXX2Nsb3VkcGlja2xlX3N1Ym1vZHVsZXOUXZSMC19fZ2xvYmFsc19flH2UdYaUhlIwLg=="}, "_last_obs": null, "_last_episode_starts": null, "_last_original_obs": null, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": 1, "ep_info_buffer": null, "ep_success_buffer": null, "_n_updates": 0, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}
+{"policy_class": {":type:": "<class 'abc.ABCMeta'>", ":serialized:": "gAWVOwAAAAAAAACMIXN0YWJsZV9iYXNlbGluZXMzLmNvbW1vbi5wb2xpY2llc5SMEUFjdG9yQ3JpdGljUG9saWN5lJOULg==", "__module__": "stable_baselines3.common.policies", "__doc__": "\n    Policy class for actor-critic algorithms (has both policy and value prediction).\n    Used by A2C, PPO and the likes.\n\n    :param observation_space: Observation space\n    :param action_space: Action space\n    :param lr_schedule: Learning rate schedule (could be constant)\n    :param net_arch: The specification of the policy and value networks.\n    :param activation_fn: Activation function\n    :param ortho_init: Whether to use or not orthogonal initialization\n    :param use_sde: Whether to use State Dependent Exploration or not\n    :param log_std_init: Initial value for the log standard deviation\n    :param full_std: Whether to use (n_features x n_actions) parameters\n        for the std instead of only (n_features,) when using gSDE\n    :param use_expln: Use ``expln()`` function instead of ``exp()`` to ensure\n        a positive standard deviation (cf paper). It allows to keep variance\n        above zero and prevent it from growing too fast. In practice, ``exp()`` is usually enough.\n    :param squash_output: Whether to squash the output using a tanh function,\n        this allows to ensure boundaries when using gSDE.\n    :param features_extractor_class: Features extractor to use.\n    :param features_extractor_kwargs: Keyword arguments\n        to pass to the features extractor.\n    :param share_features_extractor: If True, the features extractor is shared between the policy and value networks.\n    :param normalize_images: Whether to normalize images or not,\n         dividing by 255.0 (True by default)\n    :param optimizer_class: The optimizer to use,\n        ``th.optim.Adam`` by default\n    :param optimizer_kwargs: Additional keyword arguments,\n        excluding the learning rate, to pass to the optimizer\n    ", "__init__": "<function ActorCriticPolicy.__init__ at 0x7f311c7a8940>", "_get_constructor_parameters": "<function ActorCriticPolicy._get_constructor_parameters at 0x7f311c7a89d0>", "reset_noise": "<function ActorCriticPolicy.reset_noise at 0x7f311c7a8a60>", "_build_mlp_extractor": "<function ActorCriticPolicy._build_mlp_extractor at 0x7f311c7a8af0>", "_build": "<function ActorCriticPolicy._build at 0x7f311c7a8b80>", "forward": "<function ActorCriticPolicy.forward at 0x7f311c7a8c10>", "extract_features": "<function ActorCriticPolicy.extract_features at 0x7f311c7a8ca0>", "_get_action_dist_from_latent": "<function ActorCriticPolicy._get_action_dist_from_latent at 0x7f311c7a8d30>", "_predict": "<function ActorCriticPolicy._predict at 0x7f311c7a8dc0>", "evaluate_actions": "<function ActorCriticPolicy.evaluate_actions at 0x7f311c7a8e50>", "get_distribution": "<function ActorCriticPolicy.get_distribution at 0x7f311c7a8ee0>", "predict_values": "<function ActorCriticPolicy.predict_values at 0x7f311c7a8f70>", "__abstractmethods__": "frozenset()", "_abc_impl": "<_abc_data object at 0x7f311c825480>"}, "verbose": 1, "policy_kwargs": {":type:": "<class 'dict'>", ":serialized:": "gAWVowAAAAAAAAB9lCiMDGxvZ19zdGRfaW5pdJRK/v///4wKb3J0aG9faW5pdJSJjA9vcHRpbWl6ZXJfY2xhc3OUjBN0b3JjaC5vcHRpbS5ybXNwcm9wlIwHUk1TcHJvcJSTlIwQb3B0aW1pemVyX2t3YXJnc5R9lCiMBWFscGhhlEc/764UeuFHrowDZXBzlEc+5Pi1iONo8YwMd2VpZ2h0X2RlY2F5lEsAdXUu", "log_std_init": -2, "ortho_init": false, "optimizer_class": "<class 'torch.optim.rmsprop.RMSprop'>", "optimizer_kwargs": {"alpha": 0.99, "eps": 1e-05, "weight_decay": 0}}, "observation_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [28], "low": "[-inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf\n -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf -inf]", "high": "[inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf inf\n inf inf inf inf inf inf inf inf inf inf]", "bounded_below": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "bounded_above": "[False False False False False False False False False False False False\n False False False False False False False False False False False False\n False False False False]", "_np_random": null}, "action_space": {":type:": "<class 'gym.spaces.box.Box'>", ":serialized:": "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", "dtype": "float32", "_shape": [8], "low": "[-1. -1. -1. -1. -1. -1. -1. -1.]", "high": "[1. 1. 1. 1. 1. 1. 1. 1.]", "bounded_below": "[ True  True  True  True  True  True  True  True]", "bounded_above": "[ True  True  True  True  True  True  True  True]", "_np_random": null}, "n_envs": 4, "num_timesteps": 2000000, "_total_timesteps": 2000000, "_num_timesteps_at_start": 0, "seed": null, "action_noise": null, "start_time": 1677584450975645946, "learning_rate": 0.00096, "tensorboard_log": null, "lr_schedule": {":type:": "<class 'function'>", ":serialized:": "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"}, "_last_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_last_episode_starts": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "gAWVdwAAAAAAAACMEm51bXB5LmNvcmUubnVtZXJpY5SMC19mcm9tYnVmZmVylJOUKJYEAAAAAAAAAAAAAACUjAVudW1weZSMBWR0eXBllJOUjAJiMZSJiIeUUpQoSwOMAXyUTk5OSv////9K/////0sAdJRiSwSFlIwBQ5R0lFKULg=="}, "_last_original_obs": {":type:": "<class 'numpy.ndarray'>", ":serialized:": "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"}, "_episode_num": 0, "use_sde": true, "sde_sample_freq": -1, "_current_progress_remaining": 0.0, "ep_info_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "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"}, "ep_success_buffer": {":type:": "<class 'collections.deque'>", ":serialized:": "gAWVIAAAAAAAAACMC2NvbGxlY3Rpb25zlIwFZGVxdWWUk5QpS2SGlFKULg=="}, "_n_updates": 62500, "n_steps": 8, "gamma": 0.99, "gae_lambda": 0.9, "ent_coef": 0.0, "vf_coef": 0.4, "max_grad_norm": 0.5, "normalize_advantage": false, "system_info": {"OS": "Linux-5.10.147+-x86_64-with-glibc2.29 # 1 SMP Sat Dec 10 16:00:40 UTC 2022", "Python": "3.8.10", "Stable-Baselines3": "1.7.0", "PyTorch": "1.13.1+cu116", "GPU Enabled": "True", "Numpy": "1.22.4", "Gym": "0.21.0"}}

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:414d1e5e9d26742f7d34b9f5fda9ec1c58a801c85216a46f7dc6b1208cfb42f1
-size 1168224
+oid sha256:283e58e22b22049a1bb6c904b8c6f2dd5d2d7a06841e67e1953bd54e3f93e6ce
+size 1021081

results.json

@@ -1 +1 @@
-{"mean_reward": 8.4005405575037, "std_reward": 0.2948030349009093, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T11:40:27.783809"}
+{"mean_reward": 1713.606565874687, "std_reward": 89.0691661254785, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-28T12:42:21.604256"}

vec_normalize.pkl

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a492a76290837046d4e83920e944f6d78824bdfefab154ede6140f076f7abb65
-size 2123
+oid sha256:40d226276809afa79553e3f9054fc70a83c0c051833740f69242169db34495c7
+size 2136